tokenstat
tokenstat

MiniMax-M2.7-highspeed

minimax/minimax-m2.7-highspeed · rates as of · Benchmarks · Plans · Calculator

Low-latency M2.7 variant for interactive coding plans and agent loops

Cheapest input
$0.3
$/MTok · models.dev
Cheapest output
$1.20
$/MTok
Context
205K
tokens
Offers
12
1 source

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (2 omitted). Show free/$0 offers.

SourceProviderInputOutputCache readContext
models.devcheapestminimax-m2-7-highspeedEmpirioLabs AI$0.3$1.20$0.03200K
models.devminimax/minimax-m2.7-highspeedFastRouter$0.6$2.40$0205K
models.devminimax/minimax-m2.7-highspeedMerge Gateway$0.6$2.40$0.06205K
models.devMiniMax-M2.7-highspeedMiniMax$0.6$2.40$0.06205K
models.devminimax/minimax-m2.7-highspeedNovita AI$0.6$2.40$0.06205K
models.devminimax/minimax-m2.7-highspeedOrcaRouter$0.6$2.40$0.06205K
models.devminimax/minimax-m2.7-highspeedVercel AI Gateway$0.6$2.40$0.06205K
models.devminimax-m2-7-highspeedAuriko$0.6$2.40$0205K
models.devminimax-m2.7-highspeedLLM Gateway$0.6$2.40$0.06205K
models.devMiniMax-M2.7-highspeedMiniMax (minimaxi.Com)$0.6$2.40$0.06205K
models.devMiniMax-M2.7-highspeed302.AI$0.6$4.80$0205K
models.devminimax/minimax-m2.7-highspeedZenMux$0.611$2.44$0205K

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-01-01Released: 2026-03-19Family: minimax

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash